Coreference Resolution on LitBank (test)
81.8Avg. F1ImCoref-CeS
Evaluation Results
| Method | Links | |||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ImCoref-CeSBackbone=DeepSeek2025.10 | 81.8 | — | — | — | 95.3 | 83.6 | 89.1 | 82.8 | 81.1 | 81.9 | 69.4 | 80.5 | 74.5 | — | — | |
| ImCoref-CeSdpskReasoning LLM=DeepSeek2025.10 | 81.8 | 89.1 | 81.9 | 74.5 | — | — | — | — | — | — | — | — | — | — | — | |
| LLMLinkRequired Training=Multiple LLMs2025.12 | 81.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LLMLinknote=train multiple LLMs2025.10 | 81.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LLMLinkRequired training multiple LLMs=true2025.10 | 81.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MEIC-DT2025.12 | 81.3 | 87.9 | 78.5 | 77.4 | — | — | — | — | — | — | — | — | — | — | — | |
| ImCoref-CeS_gpt4Config=CeS_gpt42025.12 | 81.1 | 88.8 | 81.5 | 72.9 | — | — | — | — | — | — | — | — | — | — | — | |
| ImCoref-CeSBackbone=GPT-42025.10 | 81.1 | — | — | — | 94.8 | 83.5 | 88.8 | 82.4 | 80.6 | 81.5 | 67.2 | 79.7 | 72.9 | — | — | |
| ImCoref-CeSgpt4Reasoning LLM=GPT-42025.10 | 81.1 | 88.8 | 81.5 | 72.9 | — | — | — | — | — | — | — | — | — | — | — | |
| ImCoref-CeSBackbone=Qwen2025.10 | 80.4 | — | — | — | 95.2 | 83.1 | 88.7 | 81.3 | 79.2 | 80.2 | 66.5 | 79.1 | 72.3 | — | — | |
| ImCoref-CeSqwenReasoning LLM=Qwen2025.10 | 80.4 | 88.7 | 80.2 | 72.3 | — | — | — | — | — | — | — | — | — | — | — | |
| ImCoref_mesConfig=mes2025.12 | 79.7 | 87.9 | 79.5 | 71.6 | — | — | — | — | — | — | — | — | — | — | — | |
| ImCoref2025.10 | 79.7 | — | — | — | 93.4 | 83 | 87.9 | 79.1 | 79.9 | 79.5 | 62.8 | 83.3 | 71.6 | — | — | |
| ImCoref2025.10 | 79.7 | 87.9 | 79.5 | 71.6 | — | — | — | — | — | — | — | — | — | — | — | |
| Dual-cache2025.12 | 79.5 | 88.2 | 79.2 | 71 | — | — | — | — | — | — | — | — | — | — | — | |
| Dual-cache2025.10 | 79.5 | — | — | — | — | — | 88.2 | — | — | 79.2 | — | — | 71 | — | — | |
| Dual-cache2025.10 | 79.5 | 88.2 | 79.2 | 71 | — | — | — | — | — | — | — | — | — | — | — | |
| Maverickmes2025.10 | 78.4 | — | — | — | 94.1 | 79.9 | 86.5 | 82.2 | 75.7 | 78.8 | 59.1 | 85.2 | 69.8 | — | — | |
| Maverickmes2025.10 | 78.4 | 86.5 | 78.8 | 69.8 | — | — | — | — | — | — | — | — | — | — | — | |
| Maverick_incrConfig=incremental2025.12 | 78.3 | 86.5 | 78.8 | 69.8 | — | — | — | — | — | — | — | — | — | — | — | |
| Maverick_mesConfig=mes2025.12 | 78.1 | 86.2 | 78.4 | 69.6 | — | — | — | — | — | — | — | — | — | — | — | |
| seq2seq2025.12 | 77.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| seq2seq2025.10 | 77.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| seq2seq2025.10 | 77.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| longdoc2025.12 | 76.5 | 88.2 | 75.9 | 65.5 | — | — | — | — | — | — | — | — | — | — | — | |
| longdoc2025.10 | 76.5 | — | — | — | 90.8 | 85.7 | 88.2 | 80 | 72.1 | 75.9 | 65.1 | 66 | 65.5 | — | — | |
| longdoc2025.10 | 76.5 | 88.2 | 75.9 | 65.5 | — | — | — | — | — | — | — | — | — | — | — | |
| GPT-3.5-turbo2025.12 | 75.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GPT-3.5-turbo2025.10 | 75.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GPT-3.5-turbo2025.10 | 75.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| maverick-mes-litbankTraining Dataset=LitBank2026.05 | — | — | — | — | — | — | — | — | — | — | — | — | — | 78 | 53 | |
| maverick-mes-ontonotesTraining Dataset=OntoNotes2026.05 | — | — | — | — | — | — | — | — | — | — | — | — | — | 48 | 53 | |
| maverick-mes-precoTraining Dataset=PreCo2026.05 | — | — | — | — | — | — | — | — | — | — | — | — | — | 35 | 46 |